发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
macos-safari
Automate Safari on macOS using AppleScript. Use for opening URLs, reading page content, managing tabs/windows, executing JavaScript, and searching bookmarks/history. Triggers on queries about browsing, web pages, Safari tabs, bookmarks, or web automation.
empty-payload-sentinel-guard
Guard requests from closing instantly when a tool returns nothing by injecting the sentinel message and logging the event.
project-workflows
Official Festapp workflows. How to run tests, manage secrets, sync translations, and commit changes safely.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
headless-checkout-proxy
Apply when implementing cart, checkout, or order placement logic proxied through a BFF for headless VTEX storefronts. Covers OrderForm lifecycle, cart creation, item management, profile/shipping/payment attachments, orderFormId management, and secure checkout flows. Use for any headless frontend that needs to proxy VTEX Checkout API calls through a server-side layer with proper session cookie handling.
headless-intelligent-search
Apply when implementing search functionality, faceted navigation, or autocomplete in a headless VTEX storefront. Covers product_search, autocomplete_suggestions, facets, banners, correction_search, and top_searches endpoints, plus analytics event collection. Use for any custom frontend that integrates VTEX Intelligent Search API for product discovery and search result rendering.
vtex-io-auth-and-policies
Apply when deciding or implementing permissions and authorization boundaries for VTEX IO apps. Covers manifest policies, outbound-access rules, least-privilege design, and how service routes or integrations map to explicit permissions. Use for deciding who is authorized to call or consume a capability, adding new integrations, exposing protected routes, or reviewing app permissions for overreach or missing access.
vtex-io-storefront-react
Apply when building VTEX IO storefront components under react/ for Store Framework experiences. Covers storefront component structure, css-handles, storefront context hooks, browser-safe data fetching, and how components should behave when used as theme blocks. Use for custom storefront UI, product widgets, banners, forms, or reviewing shopper-facing React code in VTEX IO apps.
jobs-theory
Clarify what job your product actually does for people. Use when uncertain about value proposition, preparing customer interviews, writing positioning/copy, or deciding what to build. Interactive and output-focused - produces job statements, interview scripts, and opportunity analysis rather than lecturing theory.
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
athena-framework
Use this skill when working with Athena Framework for Crystal. Athena is a modular ecosystem of independent, reusable components, including: Framework (ATH) for web apps, DependencyInjection (ADI) for IoC containers, Routing (ART) for HTTP routing, Serializer (ASR) for object serialization, Validator (AVD) for validation, Console (ACON) for CLI tools, EventDispatcher (AED) for event-driven architecture, and more. Use it to build Crystal web applications, REST APIs, CLI tools, or to integrate individual components into existing projects.
fetching-claude-docs
Use PROACTIVELY before writing or modifying any Claude Code component (subagent, skill, hook, rule, slash command, plugin manifest, settings.json, MCP config) to fetch the current official spec from code.claude.com and avoid drifting from up-to-date best practices. Use when user asks 'what is the official spec for X', 'is this the right way to do Y', 'check Anthropic docs for Z'. MUST BE USED at Task 0 of writing-subagents, writing-skills, writing-hooks, writing-rules, writing-claude-md before any design decision.
postgres-patterns
PostgreSQL best practices — indexing, RLS, pagination, optimization, data types. Use when working with PostgreSQL.
dependency-mapping
Map slice dependencies using DSM matrix and prioritize by risk
qa-commit
Verify implementation against QA Contract (G#N, AC#N), auto-invoke debug on RED
arxiv-api
Search and retrieve preprints from the arXiv open-access repository
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
supporting-citations-skill
A test skill with proper source citations in supporting files.
sre-task-refinement
Use when you have to refine subtasks into actionable plans ensuring that all corner cases are handled and we understand all the requirements.
testing-anti-patterns
Use when writing or changing tests, adding mocks - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies
figma-to-generateblocks
Convert Figma designs to GenerateBlocks V2 format for WordPress
g-codebase-analysis
Deep merge of codebases you own—architecture map, vault, Galdr tasks. For external ideas only, use g-harvest, not full integration.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.